Do I always need to call RUBE_SEARCH_TOOLS before running a tool?

Yes. It fetches current tool schemas and prevents hardcoding slugs or arguments.

How do I ensure the Browserbase Tool connection is ready?

Use RUBE_MANAGE_CONNECTIONS with toolkit "browserbase_tool" and confirm the status is ACTIVE before executing.

Where should I specify memory and session details for executions?

Include memory (even as {}) and the relevant session_id in the RUBE_MULTI_EXECUTE_TOOL call, following the discovered schema.

browserbase-tool-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/browserbase-tool-automation --openclaw

Files (1)

SKILL.md

3.0 KB

Browserbase Tool Automation via Rube MCP

Automate Browserbase Tool operations through Composio's Browserbase Tool toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/browserbase_tool

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Browserbase Tool connection via RUBE_MANAGE_CONNECTIONS with toolkit browserbase_tool
Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit browserbase_tool
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "Browserbase Tool operations", known_fields: ""}]
session: {generate_id: true}

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

Core Workflow Pattern

Step 1: Discover Available Tools

RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Browserbase Tool task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["browserbase_tool"]
session_id: "your_session_id"

Step 3: Execute Tools

RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"

Known Pitfalls

Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
Pagination: Check responses for pagination tokens and continue fetching until complete

Quick Reference

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with Browserbase Tool-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `browserbase_tool`
Execute	`RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs
Bulk ops	`RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`
Full schema	`RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef`

Powered by Composio

Source

git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/browserbase-tool-automation/SKILL.md

View on GitHub

Overview

This skill automates Browserbase Tool operations through Composio's Rube MCP. It emphasizes always querying for current tool schemas before execution to avoid stale slugs. By unifying discovery, connection management, and execution, it enables end-to-end automation with proper session and memory handling.

How This Skill Works

The workflow starts by discovering available tools with RUBE_SEARCH_TOOLS to fetch current slugs and input schemas. Next, it verifies and establishes an ACTIVE connection to the browserbase_tool toolkit using RUBE_MANAGE_CONNECTIONS. Finally, it executes the chosen tool via RUBE_MULTI_EXECUTE_TOOL, providing schema-compliant arguments and a memory object, while reusing session IDs for coherence.

When to Use It

Automate an end-to-end Browserbase Tool task from discovery to execution.
When tool schemas change and you must fetch current slugs and inputs before running.
To verify or establish an ACTIVE connection to the browserbase_tool toolkit before workflows.
When executing multiple Browserbase Tool tasks in a single session workflow.
When ensuring memory handling and session reuse across tool executions and potential pagination.

Quick Start

Step 1: Verify Rube MCP is available by calling RUBE_SEARCH_TOOLS.
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["browserbase_tool"] and ensure status is ACTIVE.
Step 3: Execute a tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and memory: {}.

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch up-to-date tool schemas.
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
Use exact field names and types from the search results (no hardcoding).
Include memory: {} in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
Reuse session IDs within a workflow and handle pagination tokens if present.

Example Use Cases

Discover a Browserbase Tool slug with RUBE_SEARCH_TOOLS, then execute it via RUBE_MULTI_EXECUTE_TOOL in a single session.
Establish a browserbase_tool connection, validate ACTIVE status, and run a sequence of tools in one run.
Fetch updated tool schemas after a schema change, then re-run a previously scripted automation with new args.
Handle results pagination when listing tools, continuing to fetch until complete using RUBE_SEARCH_TOOLS.
Bulk operations: use RUBE_REMOTE_WORKBENCH and run_composio_tool() to orchestrate multiple tool executions.

Frequently Asked Questions

Add this skill to your agents